SV Atlas
← All founders
Diederik Vink

Diederik Vink

Co-Founder of nCompass Technologies Inc. (YC-W24)

2023Co-founder· nCompass Technologies Inc.
Founder · since 2023
Company
nCompass Technologies Inc.
Role
Co-Founder
current
Stage
—
no public source
Raised
—
no public source
Based
London, England, United Kingdom
current
Founder / co-founder — the company's markEmployee / research role
Source: LinkedIn work history
Profile coverage5 of 7 · missing posts, contact
nCompass Technologies logo
nCompass Technologies

Optimize performance on GPUs - 10x faster

Winter 2024

Experience

Career

  • nCompass Technologies Inc. logo

    nCompass Technologies Inc.

    Co-founder

    Co-Founder · London, England, United Kingdom · 2023 – Present

    2023
  • Undo logo

    Undo

    Engineering Consultant · Greater London, England, United Kingdom · 2023

    2023
  • Imperial College London logo

    Imperial College London

    PHD Student · London Area, United Kingdom · 2018 – 2023

    2018
  • Arm logo

    Arm

    MPG Architecture and Modelling Intern · Greater Cambridge Area · 2017

    2017
  • ARM logo

    ARM

    Systems and Software Intern · Greater Cambridge Area · 2016

    2016
  • Real Time Power, Inc. logo

    Real Time Power, Inc.

    Software Engineering Intern · Zürich Area, Switzerland · 2015

    2015
  • Real Time Power, Inc. logo

    Real Time Power, Inc.

    Software Engineer Intern · Zürich Area, Switzerland · 2014

    2014
  • NeuroTherm, Inc.

    Electrical Engineering Intern · Wilmington, MA · 2013

    2013
  • University of Zurich logo

    University of Zurich

    Brain Research Institute Intern · Zürich Area, Switzerland · 2012 – 2013

    2012

Bio

I'm a recent Imperial College London PhD Graduate where I specialized in reconfigurable hardware architectures for accelerated machine learning and reduced precision training algorithms. I have worked as an AI feasibility consultant prototyping and evaluating AI spin-outs. We are building nCompass, a platform for accelerating and hosting both open-source and custom large AI models. Our focus is on providing rate-unlimited and low latency large AI inference with only one line of code.